Suzaku is a pattern programming framework that enables programmers to create pattern-based parallel MPI programs without writing the MPI message-passing code implicit in the patterns. The purpose of this framework is ...
详细信息
ISBN:
(纸本)9781509036820
Suzaku is a pattern programming framework that enables programmers to create pattern-based parallel MPI programs without writing the MPI message-passing code implicit in the patterns. The purpose of this framework is to simplify message-passing programming and create better structured programs based upon established parallel design patterns. The focus for developing Suzaku is on teaching parallel programming. This paper covers the main features of Suzaku and describes our experiences using it in parallel programming classes.
Parallel programming has been taught for many years but has recently taken on greater significance with introduction of multicore and many-core processors. Still, most teaching has followed a traditional path of focus...
详细信息
ISBN:
(纸本)9781450318686
Parallel programming has been taught for many years but has recently taken on greater significance with introduction of multicore and many-core processors. Still, most teaching has followed a traditional path of focusing on learning low-level tools such as MPI. This workshop introduces a new educational approach based upon first selecting a computational pattern and then using higher-level tools to create parallel executable code. A pattern programming framework has been developed to create a distributed application that avoids the need to use low-level routines. The framework self-deploys on distributed computers, clusters, and individual multicore computers. Several patterns have been implemented including workpool, pipeline, synchronous and iterative all-to-all, and stencil. The first pattern covered is the widely applicable workpool pattern and other patterns will be introduced. The workshop will describe how the approach can be used in the undergraduate curriculum and will provide hands-on experiences to participants. In our approach, students focus upon computational strategies. programming is much easier and less likely to be flawed. Each workshop participant will receive a flash drive with all software and documentation pre-loaded for use in the workshop and afterwards in their classes. Laptop required.
Nano-layered films of PVAc/PU systems were fabricated by forced assembly coextrusion method. The bulk shape memory properties of PVAc/PU systems were utilized to program nanoscale patterns such as diffraction grating ...
详细信息
Nano-layered films of PVAc/PU systems were fabricated by forced assembly coextrusion method. The bulk shape memory properties of PVAc/PU systems were utilized to program nanoscale patterns such as diffraction grating which exhibit iridescence after patterning. A hot embossing process has been utilized to imprint diffraction grating patterns as nano-scale information onto the surface of the thin multilayer films. Three levels of hierarchy i.e. layer thickness, spacing and heights of patterns, governs the functionality of the patterned multilayer film. The time and temperature dependent viscoelastic shape memory behavior determines the opto-mechanical tunability of the film. Mechanical switching of the patterns also leads to optical switching of the films which corresponds to their efficiency of information retrieval. The recovery of patterns as well as the diffractive property depends on the layer thickness (l) of films and heights of patterns (h(0)). The results illustrate that the higher ratio of h(0)/l better is the recovery of the grating patterns and the corresponding diffractive properties. This scaling effect enables versatile applications in information security by tuning the layer structure of the multilayer shape memory films.
In this paper, we describe the results of teaching a parallel programming course using a pattern programming approach in a course taught across the State of North Carolina on a televideo network in Fall 2013. Five uni...
详细信息
ISBN:
(纸本)9781479941162
In this paper, we describe the results of teaching a parallel programming course using a pattern programming approach in a course taught across the State of North Carolina on a televideo network in Fall 2013. Five universities participated in this study. The course begins with a higher-level tool called the Seeds framework that creates and executes high-level message passing patterns such as a workpool without writing low level MPI code. To avoid going directly to MPI next, we used another tool (Paraguin compiler) which uses compiler directives to create MPI code for patterns. Once students understand the pattern programming approach we then present low level MPI routines and their more complex parameters but now with the knowledge of parallel patterns. An independent professional evaluator is employed to deploy survey instruments and produce an analysis of the results. The lessons we learned from this data collected in Fall 2013 are: 1) Teaching parallel computing in the context of patterns has a positive impact on student learning;2) Teaching the lower level tools first would be beneficial;3) The improvements made to the Paraguin compiler directives significantly improved the students confidence in using the tool;and 4) The lower level tools can still be taught in the context of patterns.
Tissue-specific natural anisotropic microstructures play an important role in the normal functioning of tissues, yet they remain difficult to construct by current printing techniques. Herein, a stepwise algorithm-assi...
详细信息
Tissue-specific natural anisotropic microstructures play an important role in the normal functioning of tissues, yet they remain difficult to construct by current printing techniques. Herein, a stepwise algorithm-assisted bioprinting technology for the construction of biomimetic tissues with a customizable anisotropic microstructure by combining the Adaptive Mesh Generation algorithm and the Greedy Search algorithm is developed. Based on the mechanical topology optimization design mechanism, the Adaptive Mesh Generation algorithm can generate controllable anisotropic mesh patterns with the minimum free energy in plane models according to tissue-specific requirements. Subsequently, the Greedy Search algorithm can program the generated pattern data into optimized printing paths, effectively avoiding structural deformations caused by the multiple stacking of materials and reducing the printing time. The developed bioprinting technique is suitable for various types of bioinks including polymers, hydrogels, and organic/inorganic complexes. After combining with a calcium phosphorus bioink, the compound algorithm-assisted bioprinting technique successfully customizes femurs with biomimetic chemical compositions, anisotropic microstructures, and biological properties, demonstrating its effectiveness. Additionally, algorithm-assisted bioprinting is generally suitable for most commercial extrusion bioprinters that function in the geometric code (G-code) drive mode. Therefore, the algorithm-assisted extrusion bioprinting technology offers an intelligent manufacturing strategy for the customization of anisotropic microstructures in biomimetic tissues.
暂无评论